- 04 Oct, 2021 1 commit
-
-
Philip Meier authored
* add ufmt as code formatter * cleanup * quote ufmt requirement * split imports into more groups * regenerate circleci config * fix CI * clarify local testing utils section * use ufmt pre-commit hook * split relative imports into local category * Revert "split relative imports into local category" This reverts commit f2e224cde2008c56c9347c1f69746d39065cdd51. * pin black and usort dependencies * fix local test utils detection * fix ufmt rev * add reference utils to local category * fix usort config * remove custom categories sorting * Run pre-commit without fixing flake8 * got a double import in merge Co-authored-by:Nicolas Hug <nicolashug@fb.com>
-
- 30 Sep, 2021 1 commit
-
-
Vasilis Vryniotis authored
* Moving _make_divisible to utils. * Replace the old ConvBNReLU and ConvBNActivation layers * Fix minor bug. * Moving SE layer to ops. * Adding deprecation warnings on old layers. * Apply changes to regnets.
-
- 22 Jun, 2021 1 commit
-
-
Nicolas Hug authored
-
- 25 May, 2021 1 commit
-
-
Vasilis Vryniotis authored
* Fix a bug when trainable_layers == 0 * Fix same issue on ssd.
-
- 18 May, 2021 2 commits
-
-
Vasilis Vryniotis authored
* Remove incorrect params from doc and add references to the paper. * Add paper links in doc.
-
Nicolas Hug authored
-
- 13 May, 2021 1 commit
-
-
Vasilis Vryniotis authored
* Converting private parameters to public. * Add kwargs to handle extra params. * Add another kwargs. * Add arguments in _mobilenet_extractor.
-
- 12 May, 2021 1 commit
-
-
Vasilis Vryniotis authored
-
- 11 May, 2021 1 commit
-
-
Vasilis Vryniotis authored
* Partial implementation of SSDlite. * Add normal init and BN hyperparams. * Refactor to keep JIT happy * Completed SSDlite. * Fix lint * Update todos * Add expected file in repo. * Use C4 expansion instead of C4 output. * Change scales formula for Default Boxes. * Add cosine annealing on trainer. * Make T_max count epochs. * Fix test and handle corner-case. * Add support of support width_mult * Add ssdlite presets. * Change ReLU6, [-1,1] rescaling, backbone init & no pretraining. * Use _reduced_tail=True. * Add sync BN support. * Adding the best config along with its weights and documentation. * Make mean/std configurable. * Fix not implemented for half exception
-